Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    distinctive formatting elements indicative of structured information or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     another
    -0.07
    alias
    -0.07
     like
    -0.06
     Nose
    -0.06
     specifically
    -0.06
    .global
    -0.06
     reward
    -0.06
    allet
    -0.06
    eb
    -0.06
    another
    -0.06
    POSITIVE LOGITS
     :↵
    0.09
     :↵↵
    0.09
    ):↵
    0.09
     ):↵
    0.08
    ():↵
    0.08
    ':↵
    0.08
     besides
    0.08
     []:↵
    0.08
     ):↵↵
    0.08
    GenerationStrategy
    0.08
    Act Density 0.022%

    No Known Activations